{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:53:01Z","timestamp":1782834781388,"version":"3.54.5"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1736202"],"award-info":[{"award-number":["U1736202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/taslp.2020.2988423","type":"journal-article","created":{"date-parts":[[2020,4,20]],"date-time":"2020-04-20T19:56:47Z","timestamp":1587412607000},"page":"1385-1394","source":"Crossref","is-referenced-by-count":23,"title":["Improving End-to-End Single-Channel Multi-Talker Speech Recognition"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4500-3515","authenticated-orcid":false,"given":"Wangyou","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5221-5412","authenticated-orcid":false,"given":"Xuankai","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0314-3790","authenticated-orcid":false,"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5970-8631","authenticated-orcid":false,"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1728"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2012.6271907"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3192"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682822"},{"key":"ref30","first-page":"1","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2014","journal-title":"NIPS 2014 Deep Learning and Representation Learning Workshop"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2647702"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2297012"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.003"},{"key":"ref34","first-page":"3274","article-title":"Speech enhancement using compressed sensing","author":"abrol","year":"0","journal-title":"Proc ISCA Interspeech"},{"key":"ref28","first-page":"2654","article-title":"Do deep nets really need to be deep","author":"ba","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref29","first-page":"1910","article-title":"Learning small-size DNN with output-distribution-based criteria","author":"li","year":"0","journal-title":"Proc ISCA Interspeech"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639347"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1547"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461883"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.09.003"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1244"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461893"},{"key":"ref26","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref50","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc Autom Speech Recognition Understanding Workshop"},{"key":"ref51","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc ICLR"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref55","first-page":"137","article-title":"The AMI meeting corpus","volume":"88","author":"mccowan","year":"0","journal-title":"Proc Int Conf Methods Tech Behav Res"},{"key":"ref54","article-title":"ADADELTA: An adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"arXiv 1212 5701"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref52","first-page":"338","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"0","journal-title":"Proc ISCA Interspeech"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907229"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1037\/0735-7036.122.3.235"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700814"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-305"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2765834"},{"key":"ref4","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461870"},{"key":"ref6","article-title":"End-to-end continuous speech recognition using attention-based recurrent NN: First results","author":"chorowski","year":"2014","journal-title":"NIPS 2014 Deep Learn Repres Learn Workshop"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref49","year":"1993","journal-title":"LDC Catalog CSR-I (WSJ0) Complete"},{"key":"ref9","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","author":"amodei","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2700540"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765695"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1025"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1048"},{"key":"ref41","first-page":"437","article-title":"Cracking the cocktail party problem by multi-beam deep attractor network","author":"chen","year":"0","journal-title":"Proc IEEE Workshop Autom Speech Recognit Understanding"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1137"},{"key":"ref43","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"0","journal-title":"Proc ICLR"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/09072433.pdf?arnumber=9072433","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:31:25Z","timestamp":1651080685000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9072433\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.2988423","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}